Austo Automobiles
Data-Driven Insights on Customer Purchase
Behavior
A Business Intelligence Report for Strategic Marketing Campaign
Report by:
Sanjay Patel
Date:
October 19, 2025
List of Figures
Figure No. Figure Name Page
Figure 1 Age Distribution 4
Figure 2 Box Plot of Age 4
Figure 3 Total Salary Distribution 5
Figure 4 Box Plot of Total Salary 5
Figure 5 Price Distribution 6
Figure 6 Box Plot of Price 6
Figure 7 Make Distribution 7
Figure 8 Analysis of Partner Working Status 7
Figure 9 Analysis of House Loan Status 8
Figure 10 Correlation Matrix Heatmap of Numerical Variables 9
Figure 11 Relationship Between Car Price and Customer Age by Make 10
Figure 12 Relationship Between Salary and Age by Make 10
Figure 13 Profession Distribution by Gender 11
Figure 14 Gender Preference by Make 11
Figure 15 Make Preference by Profession 12
Figure 16 Profession by Make Preference 12
Figure 17 Relationship Between Price and Age by Partner Working Status 14
List of Tables
Table No. Table Name Page
Table 1 Statistical Summary of Numerical Variables 3
Table 2 Data Shape (Rows and Columns) 3
Table 3 Column Information, Non-Null Count, and Data Types 3
Table 4 Missing Value Count by Column 4
Table 5 Categorical Variable Summary 7
Table 6 Price Spent (Count, Sum, Mean) by Gender 13
Table 7 Total Price Spent by Personal Loan Takers 13
Data Dictionary
Fields Description
Age The age of the individual in years.
Gender
The gender of the individual, categorized as male or female.
Profession The occupation or profession of the individual.
Marital_status
The marital status of the individual, such as married &, single
Education The educational qualification of the individual Graduate and
Post Graduate
No_of_Dependents The number of dependents (e.g., children, elderly parents)
that the individual supports financially.
Personal_loan A binary variable indicating whether the individual has taken a
personal loan "Yes" or "No"
House_loan A binary variable indicating whether the individual has taken a
housing loan "Yes" or "No"
Partner_working A binary variable indicating whether the individual's partner is
employed "Yes" or "No"
Salary The individual's salary or income.
Partner_salary
The salary or income of the individual's partner, if applicable.
Total_salary The total combined salary of the individual and their partner
(if applicable).
Price The price of a product or service.
Make The type of automobile
CriteriaData Overview
1.1- Import the libraries (Done in Google Colab)
1.2- Load the data (Done in Google Colab)
1.3- Check the structure of the data
1.4- Check the types of the data
1.5- Check for and treat (if needed) missing values
1.6- Check the statistical summary
1.7- Check for and treat (if needed) data irregularities
1.8- Observations and Insights
Univariate Analysis
2.1 Explore all the variables (categorical and numerical) in the data
2.2 Check for and treat (if needed) outliers
2.3 Observations and Insights
Bivariate Analysis
3.1 Explore the relationship between all numerical variables
3.2 Explore the correlation between all numerical variables
3.3 Explore the relationship between categorical vs numerical variables
Explore the data to answer the following key questions:
1. Do men tend to prefer SUVs more compared to women?
2. What is the likelihood of a salaried person buying a Sedan?
3. What evidence or data supports Sheldon Cooper's claim that a salaried male is an easier
target for a SUV sale over a Sedan sale?
4. How does the the amount spent on purchasing automobiles vary by gender?
5. How much money was spent on purchasing automobiles by individuals who took a
personal loan?
6. How does having a working partner influence the purchase of higher-priced cars?
1.3 Structure of the data
1.3.1Shape:
We have following rows and columns in our report
1.3.2Following are the Columns, information about null and Data Type:
1.3.3Data Sample of first 5 rows
1.4- Check the types of the data
1.5- Check for and treat (if needed) missing values
Column Missing Value %of
Gender 53 3.4%
Partner_salary 106 6.7%
For Gender we will impute the missing values with Mode to include the variable which is more
probable to fit in there
For Partner_salary we will impute the missing value with median to include better estimates and
avoid any skewed value.
For missing values of Salary it is feasible to replace with Median of other data and for Gender we can
replace missing data with Mode.
1.6- Check the statistical summary
Statistical summary :
1.7- Check for and treat (if needed) data irregularities
We can check the column for unique variables to find any data anomaly
On checking Gender it was found there were 2 following anomalies which was converted to
expected value (Female)
Femal
Femle
We will replace “Femal” and “Femle” with right value “Female”
1.8- Observations and Insights
More than 75% of buyers have 2 or more dependents, which shows there is more possibility that
people with dependents are more likely to buy cars compared to people with no or 1
dependents
It can be said that at least partner of one fourth of buyer are not working.
Majority of the potential buyer fall in the age group of 25-38 years
Average salary of car buyer is around $60,000
2.1 Explore all the variables (categorical and numerical) in the data
2.2 Check for and treat (if needed) outliers
2.3 Observations and Insights
Age:
Observation:
Slightly Data for age is right skewed and thus we have slightly higher mean (31.9) than median
(29)
More than half of the buyers are between the age 25-40 years
Total Salary
Observation:
Box plot shows a normal distribution suggesting mean and median around 80,000
We also observe certain outliers in the analysis as well but for this analysis we need not treat
those as those are valid and meaningful data.
Price:
Observation:
Most of the cars fall in the price range of 20000 to 35000
Distribution is right skewed so Mean is higher than Median
Make:
Observation:
Most of the buyers prefer Sedan over SUV and Hatchback
Partner_Working
Observation:
55% of buyer’s partner are working. So, this factor is significant but less than expected.
House_Loan:
Observation:
Majority of the buyer does not have House loan which shows strong co-relation that people with
on going Home loan do not like to put extra burden of Buying car.
3.1 Explore the relationship between all numerical variables
3.2 Explore the correlation between all numerical variables
3.3 Explore the relationship between categorical vs numerical variables
Observation:
Heatmap shows strong correlation between Age and Price which denotes that people with
higher age tends to buy high Priced cars
Partner salary is not having much strong correlation with Price
Age and Salary shows obvious correlation. Salary should be increasing with age.
Observation:
We see clear preference of Low age buyer is Hatchback. Buyer with age group 30-45 prefer Sedan
while age group above 45 prefers SUV
Observation:
With age, salary is increasing and we combinely say people with higher age and more salary prefer
SUV followed by Sedann and Hatchback respectively.
Question 1: Do men tend to prefer SUVs more compared to women
Answer: No, women prefers SUV compared to men. Through both the plots it is clear that Women
prefer SUV over Sedan and Hatchback. Also, SUV is bought more by women compared to [Link]
bough SUV around 9% times while women bought SUV around 52% of the times they bought any cars.
Question 2: What is the likelihood of a salaried person buying a Sedan?
Answer: Salaries person buys Sedan 44%, hatchback 33% and SUV 23%. So, it is high probability that
salaried person will buy Sedan.
Question 3: What evidence or data supports Sheldon Cooper's claim that a salaried male is an
easier target for a SUV sale over a Sedan sale?
Answer: Above analysis does not support Sheldon Cooper’s claim that male is easier target for SUV
over Sedan. Sedan and Hatchback are clear preference for male over SUV.
Question4: How does the the amount spent on purchasing automobiles vary by gender?
Answer: Total spent by Male is much higher due to high volume but average spent of Female(47,705)
is much higher than male (32,416) due to purchase of high end cars (SUV)
Question5: How much money was spent on purchasing automobiles by individuals who took a
personal loan?
Question6: How does having a working partner influence the purchase of higher-priced cars?
Answer: As we had seen earlier also that correlation between Partner salary and Price was low(0.17)
and even for looking specifically for higher priced cars through this scatter plot we can conclude that
we have sufficient population of buyer without partner salary buying higher priced cars. So, factor of
working partner does not impact the purchase of higher priced cars.
Final observation, insights and recommendations:
Marketing team should target the prospective customers based on age to have better
conversion. Following strategy can be adopted for same:
Market Hatchbacks to the 22-30 age group.
Market Sedans to the 30-45 age group.
Market SUVs to the over-45 age group.
Justification: This is based on the strong price/age segmentation clearly visible in Figure 11.
Focus high-end SUV promotions and inventory on the female demographic, as they have the
highest average transaction value.
Justification: Table 6 proves women spend more on average, and Figure 14 shows their
majority preference for SUVs.
As we have observed in our analysis that people with 2 or more dependents forms 75% of total
buyers, marketing team can plan their advertisement and strategy to portray the picture around
safety, comfort and focus prospective buyers with dependents.
The observation that the majority of buyers do not have a house loan (Figure 9) suggests that
people without heavy debts are more likely to go for buying a new car compared to a person
with ongoing House loan. So, marketing team should try to get the information and focus their
campaigns on people without ongoing loans